introduction to natural language processing heshaam faili [email protected] university of...
TRANSCRIPT
Introduction to Natural Language Processing
Heshaam [email protected] of Tehran
2
What is Language? Formal Description
A Set of Symbols which … Psychological Description
A communication tools Empirical Description
A set of following items How are you? Are you ok? I am going to .. …
3
What is NLP?
Natural Language Processing (NLP) Computers use (analyze, understand,
generate) natural language A somewhat applied field
Computational Linguistics (CL) Computational aspects of the human
language faculty More theoretical
4
Why Study NLP? Human language interesting &
challenging NLP offers insights into language
Language is the medium of the web Interdisciplinary: Ling, CS, psych, math Help in communication
With computers (ASR, TTS) With other humans (MT)
Ambitious yet practical
5
Goals of NLP Scientific Goal
Identify the computational machinery needed for an agent to exhibit various forms of linguistic behavior
Engineering Goal Design, implement, and test
systems that process natural languages for practical applications
6
Applications speech processing: get flight information or
book a hotel over the phone information extraction: discover names of
people and events they participate in, from a document
machine translation: translate a document from one human language into another
question answering: find answers to natural language questions in a text collection or database
summarization: generate a short biography of Noam Chomsky from one or more news articles
7
Reference Daniel Jurafsky
James H. Martin An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition Prentice-Hall, 2000
8
Course contents…
Overview Chapter (1)
1 session
Regular expressions & Automata
Chapter (2)
2 session
Morphology & Finite-State Transducers (FSTs)
Chapter (3)
1-2 session
Spelling checking (maybe)
Chapter (5)
2 session
9
Course contents…
N-grams Chapter (6)
2 session
HMM (maybe) Chapter (7)
1 session
Part-of-speech (POS) tagging
Chapter (8)
4 session
Context-Free Grammars Chapter (9)
2 session
10
Course contents…
Parsing Chapter (10)
2 session
Unification-based parsing
Chapter (11)
2 session
Lexicalized & Probabilistic parsing
Chapter (12)
2 session
Machine Translation Chapter (21) and …
2 session
11
Other Course Activities Maintenance the homepage of
Course & NLP LAB Student Presentation (some
subjects will be announced) Different projects (usually work on
Persian language) Some Project implementation by
Perl Language
12
Evaluation
1 midterm exam : 5-6 degree 1 final term exam : 8 degree Paper presentation: 1-2 degree Some projects : 3-4 degree Some quizzes: 1 degree Some practices: 1 degree Paper publication: 1-4 added degree